knowledge-ops

Use when a Head of Ops, Knowledge Manager, or TPM-Internal needs to author, validate, or clean up company SOPs and internal runbooks (procurement intake, vendor offboarding, incident-comms cascade, employee onboarding) — including 5W2H completeness checks (Who-What-When-Where-Why-How-HowMuch), cross-link and orphan-page validation across a sprawling Notion/Confluence/Obsidian wiki, KB ingestion + hygiene reporting, and runbook step verification (named owner, expected duration, observable success signal, rollback path, escalation contact). Pairs Ishikawa's 5W2H method, Gawande's *The Checklist Manifesto*, ISO 9001, ITIL v4, and Google SRE Workbook runbook discipline with deterministic stdlib-only Python tools that score completeness, detect anti-patterns, and emit prioritized cleanup lists (e.g., "validate this runbook before it goes into rotation", "audit our Confluence wiki for stale and orphaned SOPs").

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with exact commands, flags, thresholds, and a runnable example, plus a clear sequenced workflow with a feedback loop and one-level-deep references. The main weakness is conciseness: the inline forcing-question library with canon citations and the long distinct-from section are reference-grade material better moved out of the overview.

Suggestions

Move the 7-question forcing-question library (with its per-question Canon citations) into a dedicated reference file such as references/forcing_questions.md, leaving a one-line pointer in SKILL.md to reduce inline tokens.

Tighten the 'Distinct from' section into a compact table or short bullet list; the current prose re-explains sibling skills at a length that competes with the core workflow for context budget.

Make the inter-step validation explicit gates (e.g., 'Do not proceed to step 3 until step 2's runbooks all score ≥ 60') so the feedback loop reads as a checkpoint rather than a single verification sentence.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence — no 'what is an SOP' padding, tight script descriptions — but the inline 7-question forcing-question library with per-question canon citations and a long 'Distinct from' section are reference-grade material that could be trimmed or moved to references/, keeping it just above the 'mostly efficient' anchor rather than at fully lean 5.	4 / 5
Actionability	Fully executable guidance throughout: exact script invocations with flags (`kb_ingester.py --input <vault-dir>`, `sop_generator.py --profile <ops\|support\|finance\|hr\|it\|regulated>`), explicit scoring thresholds (≥80 SAFE-TO-USE, <60 NOT-SAFE), `--sample` flags, and a copy-paste Quick example — matching the 'fully executable, copy-paste ready' anchor with no gaps.	5 / 5
Workflow Clarity	A clear four-step sequence is present with an explicit feedback loop (step 4 re-runs the ingester to verify orphan count is down) and validation via the runbook validator's MUST-FIX list, but the inter-step checkpoints are described at a high level rather than as explicit gate-before-proceeding checks, placing it between the 4 and 5 anchors.	4 / 5
Progressive Disclosure	Good structure with an overview SKILL.md pointing to three clearly-signaled, one-level-deep reference files (verified to be terminal, no nested onward references) and appropriately bundled scripts/assets, but the lengthy inline forcing-question library is content that could live in its own reference file, so it sits at 'good structure, minor organization gaps' rather than a clean 5.	4 / 5
	Total	17 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it explicitly covers both what the skill does and when to use it, with concrete actions and natural trigger phrases tied to named ops personas. The only soft spots are canon citations that are not user-spoken trigger terms and a slight overlap risk with sibling runbook/process skills.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — author/validate/clean up SOPs and runbooks, 5W2H completeness checks, cross-link and orphan-page validation, KB ingestion + hygiene reporting, runbook step verification with six named attributes — matching the comprehensive-coverage anchor rather than the 'several with minor gaps' anchor at 4.	5 / 5
Completeness	Explicitly answers both WHAT (author/validate/clean up SOPs and runbooks, deterministic tools that score completeness, detect anti-patterns, emit cleanup lists) and WHEN (opens with 'Use when a Head of Ops, Knowledge Manager, or TPM-Internal needs to...' plus concrete example triggers), matching the anchor that requires both answered with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('validate this runbook before it goes into rotation', 'audit our Confluence wiki for stale and orphaned SOPs', named personas) plus synonyms (SOP/runbook/wiki/KB), but lacks file-extension triggers and includes canon citations (Ishikawa, Gawande, ISO 9001) that users would not actually say, placing it just above the 4 anchor rather than at 5.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche — organizational SOP/runbook authoring plus KB hygiene for named ops personas across Notion/Confluence/Obsidian — with minimal conflict risk, but 'company SOPs' lightly overlaps sibling process/runbook skills, so it sits above the 'mostly distinct' anchor at 4 rather than cleanly at 5.	4 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: business-operations/skills/knowledge-ops/SKILL.md
Commit: 19392f7

Reviewed: ~13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.